← ClaudeAtlas

ccc-e2elisted

end-to-end pre-release assessment. Fans out via /ccc-fleet into 3 isolated worktrees (QA audit + unit tests + Playwright E2E), each invoking /ccc-testing sub-skills,…
KevinZai/commander · ★ 3 · Testing & QA · score 82
Install: claude install-skill KevinZai/commander
# /ccc-e2e — End-to-End Pre-Release Assessment **CC Commander** · /ccc-e2e · Full-surface confidence before you ship Composes /ccc-fleet + /ccc-testing to run a full pre-release assessment in parallel across 3 isolated worktrees. One command. Three workers. One verdict. ## Session markers Call `mcp__ccd_session__mark_chapter` at these phase transitions: | Trigger | title | summary | |---------|-------|---------| | After user confirms scope, before fan-out | `"E2E assessment: <branch>"` | `"3-worker fan-out starting on <branch>"` | | When all workers have reported back | `"E2E workers complete"` | `"QA: <status> / Unit-TDD: <status> / E2E: <status>"` | | After verdict is written | `"E2E verdict: <PASS/FAIL>"` | `"<N> Critical, <N> High — verdict: <PASS/FAIL>"` | ## Sidebar chips (spawn_task) After the verdict is rendered, spawn ONE `mcp__ccd_session__spawn_task` chip per **Critical** finding: - `title`: imperative fix phrase under 60 chars - `prompt`: self-contained — include the worker that reported it, file:line if available, issue summary, and fix direction. The spawned session has no memory of this conversation. - `tldr`: 1-2 sentences plain English. Only Critical findings get chips. High/Medium/Low go into the verdict artifact as TodoWrite items. ## Response shape (EVERY time) ### 1. Brand header ``` **CC Commander** · /ccc-e2e · Full-surface pre-release confidence ``` ### 2. Context strip Four parallel reads (silent on failure): - `git rev-parse --abbrev-r